Artificial intelligence in the diagnosis of multiple sclerosis using brain imaging modalities: A systematic review and meta-analysis of algorithms.
Authors
Affiliations (4)
Affiliations (4)
- Faculty of Paramedical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
- Department of Health Information Technology and Management, School of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
- Department of Computer, Yadegar-e-Imam Khomeini (RAH), Shahre Rey Branch, Islamic Azad University, Tehran, Iran.
- Department of Neurology, Ghaem Hospital, Mashhad University of Medical Sciences, Mashhad, Iran.
Abstract
Multiple sclerosis (MS) diagnosis remains challenging due to its heterogeneous clinical manifestations and the absence of a definitive diagnostic test. Conventional magnetic resonance imaging, while central to diagnosis, faces limitations in specificity and inter-rater variability. Artificial intelligence offers promising solutions for enhancing medical imaging analysis in MS, yet its efficacy requires systematic validation. This systematic review and meta-analysis followed Preferred Reporting Items for Systematic Review and Meta-Analysis guidelines. We searched Embase, PubMed, Web of Science, Scopus, Google Scholar, and gray literature (inception to January 5, 2025) for case-control studies applying AI to magnetic resonance imaging-based MS diagnosis. A random-effects model pooled sensitivity, specificity, and accuracy. Heterogeneity was assessed via the Q-statistic and I². Meta-regression evaluated pixel count impact. Meta-analysis revealed pooled sensitivity, specificity, and accuracy of 93%, 95%, and 94%, respectively, showcasing the efficacy of AI models in MS diagnosis. Additionally, meta-regression analysis showed no significant correlation between the number of pixels and diagnostic performance parameters. Sensitivity analysis confirmed the robustness of results, while publication bias assessment indicated no evidence of bias. AI-based algorithms show promise in augmenting traditional diagnostic approaches for MS, offering accurate and timely diagnosis. Further research is warranted to standardize AI methodologies and optimize their integration into clinical practice. This study contributes to the growing evidence supporting AI's role in enhancing diagnostics and patient care in MS.